• The Transactions of the Korean Institute of Power Electronics
• /
• v.13 no.4
• /
• pp.287-294
• /
• 2008

This paper describes an implementation of a wide-range dimming controller of a LED backlight for Avionics applications such as a control display unit(CDU) and multi-function display(MFD). The digital dimming controller employing a current controlled buck converter and light sensor feedback is proposed. The proposed system provides a wide dimming control range of from 150fL to 0.05fL(3000:1) required for avionic displays. The experimental results are provided to show the control performance.

• The Journal of Korea Robotics Society
• /
• v.11 no.2
• /
• pp.60-72
• /
• 2016

This study proposes a multi-robot system, using multiple autonomous robots, to explore concrete structures and assist in their maintenance by sealing any cracks present in the structure. The proposed system employed a new self-localization method that is essential for autonomous robots, along with a visualization system to recognize the external environment and to detect and explore cracks efficiently. Moreover, more efficient crack search in an unknown environment became possible by arranging the robots into search areas divided depending on the surrounding situations. Operations with increased efficiency were also realized by overcoming the disadvantages of the infeasible logical behavioral model design with only six basic behavioral strategies based on distributed control-one of the methods to control swarm robots. Finally, this study investigated the efficiency of the proposed multi-robot system via basic sensor testing and simulation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.2
• /
• pp.53-61
• /
• 2016

Extracting focused object with saliency map is still remaining as one of the most highly tasked research area around computer vision for it is hard to estimate. Through this paper, we propose enhanced object extraction method based on multi-channel saliency map which could be done automatically without machine learning. Proposed Method shows a higher accuracy than Itti method using SLIC, Euclidean, and LBP algorithm as for object extraction. Experiments result shows that our approach is possible to be used for automatic object extraction without any previous training procedure through focusing on the main object from the image instead of estimating the whole image from background to foreground.

• Nuclear Engineering and Technology
• /
• v.54 no.2
• /
• pp.462-468
• /
• 2022

The selection and effective utilization of peak-fitting software for conventional gamma-ray spectrum analysis is significant for accurate determination of the mass fraction of elements, particularly in complex peak regions. Majority of the peak-fitting programs can derive similar peak characteristics for singlet peaks, but very few programs can deconvolute multi-peaks in a complex region. The deconvolution of multi-peaks requires special peak-fitting functions, such as left and right-skew distributions. In the this study, 843.76 keV (²⁷Mg) peak area from the complex region (840 keV-850 keV) determined and compared using four different peak-fitting programs, namely, GammaVision, Genie2000, HyperLab, and HyperGam. The 843.76 keV peak interfered with 841.63 keV (^152mEu) and 846.81 keV (⁵⁶Mn). The total Mg concentration was determined through k₀-instrumental neutron activation analysis by applying the isotopic interference correction factor ²⁷Al(n,p)²⁷Mg through the simultaneous determination of Al concentration. HyperLab and HyperGam peak-fitting programs reported consistent peak areas, and resultant concentrations agreed with the certified values of matrix-certified reference materials.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.39-51
• /
• 2022

Image-based gender classification and age estimation of human are classic problems in computer vision. Most of researches in this field focus just only one task of either gender classification or age estimation and most of the reported methods for each task focus on accuracy performance and are not computationally light. Thus, running both tasks together simultaneously on low cost mobile or embedded systems with limited cpu processing speed and memory capacity are practically prohibited. In this paper, we propose a novel light-weight gender classification and age estimation method based on ensemble multitasking deep learning with light-weight processing neural network architecture, which processes both gender classification and age estimation simultaneously and in real-time even for embedded systems. Through experiments over various well-known datasets, it is shown that the proposed method performs comparably to the state-of-the-art gender classification and/or age estimation methods with respect to accuracy and runs fast enough (average 14fps) on a Jestson Nano embedded board.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.614-616
• /
• 2021

The world faces difficulties in terms of eye care, including treatment, quality of prevention, vision rehabilitation services, and scarcity of trained eye care experts. However, it is difficult to develop a method for classifying various ocular diseases because the existing dataset for retinal image disclosure does not consist of various diseases found in clinical practice. We propose a method for classifying ocular diseases using the Retinal Fundus Multi-disease Image Dataset (RFMiD), a dataset published in the ISBI-2021 challenge. Our goal is to develop a robust and generalizable model for screening retinal images into normal and abnormal categories. The performance of the proposed model shows a value of 0.9782 for the test dataset as an area under the curve (AUC) score.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.422-424
• /
• 2021

In this paper, it leads the approach of fusing multiple RGB cameras for visual objects recognition based on deep learning with convolution neural network and 3D Light Detection and Ranging (LiDAR) to observe the environment and match into a 3D world in estimating the distance and position in a form of point cloud map. The goal of perception in multiple cameras are to extract the crucial static and dynamic objects around the autonomous vehicle, especially the blind spot which assists the AV to navigate according to the goal. Numerous cameras with object detection might tend slow-going the computer process in real-time. The computer vision convolution neural network algorithm to use for eradicating this problem use must suitable also to the capacity of the hardware. The localization of classified detected objects comes from the bases of a 3D point cloud environment. But first, the LiDAR point cloud data undergo parsing, and the used algorithm is based on the 3D Euclidean clustering method which gives an accurate on localizing the objects. We evaluated the method using our dataset that comes from VLP-16 and multiple cameras and the results show the completion of the method and multi-sensor fusion strategy.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.541-543
• /
• 2022

In recent years, retinal disorders have become a serious health concern. Retinal disorders develop slowly and without obvious signs. To avoid vision deterioration, early detection and treatment are critical. Optical coherence tomography (OCT) is a non-invasive and non-contact medical imaging technique used to acquire informative and high-resolution image of retinal area and underlying layers. Disease signs are difficult to detect because OCT images have many areas which are not related to any disease. In this paper, we present a deep learning-based method to perform multi-label classification on a long-tailed OCT dataset. Our method first extracts the region of interest and then performs the classification task. We achieve 98% accuracy, 92% sensitivity, and 99% specificity on our private OCT dataset. Using the heatmap generated from trained convolutional neural network, our method is more robust and explainable than previous approaches because it focuses on areas that contain disease signs.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1671-1678
• /
• 2023

The Korea multi-purpose satellite (KOMPSAT) series consisting of multi-sensors has been used in various fields such as land, environmental monitoring, and disaster analysis since its first launch in 1999. Recently, as various information processing technologies (high-speed computing technology, computer vision, artificial intelligence, etc.) that are rapidly developing are utilized in the field of remote sensing, it has become possible to develop more various satellite image processing and analysis algorithms. In this special issue, we would like to introduce recently researched technologies related to the KOMPSAT image application and research topics participated in the 2023 Satellite Information Application Contest.

• Asia pacific journal of information systems
• /
• v.32 no.3
• /
• pp.630-655
• /
• 2022

This paper examines the integrated QR code payment service (QRIS) adoption by retailers in Indonesia. Indonesia started its cashless journey in 2017 by using electric money in card form. As the country keeps developing, Indonesia has planned to integrate its payment towards a cross-border payment using QR codes by 2025 in the South East Asian region. Facing government vision, MSMEs that act as the significant economy wheel in Indonesia was required to be prepared to face the multi-cultural, multi-currency, and the new tech innovation for doing transactions. However, as a developing country, Indonesia faced significant problems with its infrastructure, which made it hard for merchants to access digital payment. As infrastructure was a common problem for developing countries, Indonesia also faced financial inclusion, lack of digital knowledge, a high amount of cash use, and socialization that made low digital payment penetration. Therefore, as there was a need to increase digital payment penetration for ASEAN integrated payment, this study found that merchant compatibility, facilitating conditions, trust, and relative advantages are drivers for MSMEs using this payment method. Further, this research provides propositions for banks, financial institutions, and governments to develop and evolve towards a cashless ecosystem, especially for a country lacking infrastructure.